Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.

Hivemind turns your traces into reusable skills across agents

The open-source memory operating system for AI agents. Persistent memory, semantic search, loop detection, agent messaging, crash recovery, and real-time observability.

Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.

🚀 Build powerful agents and configurations with the complete collection of Claude Code from an Anthropic hackathon winner, refined over 10+ months.

Edge-first AI memory engine. Rust core, DuckDB single-file, sub-10ms search, 6 language bindings.

Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Claude & any MCP client persistent cross-session memory.

Geometric agent memory for Grok Build: 8-tool lean contract, harness injection at wake, session handoff. 66 MCP tools. Not a vector DB. Rust + MCP.

Deprecated split repo; AtomicMemory Core now lives in atomicstrata/atomicmemory/packages/core.

MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.

Persistent cross-session memory for AI coding assistants. Works with Claude Code, Cursor, Windsurf, Cline, OpenClaude, and MCP-compatible editors.

Local-first memory and prompt-cache layer for Claude Code

Team memory sharing for claude-mem — sync AI memories across developers, with Claude Code plugin, github action and knowledge distillation

Persistent memory for GitHub Copilot — never lose context across chat sessions. Inspired by claude-mem.

A deterministic, high-performance memory engine. Built in Rust.

Open-source AI memory engine for agents: multimodal memory, temporal knowledge graphs, graph RAG, and evidence-backed long-term context.

An embedded, deterministic, versioned memory engine and state-tracker for long-lived programs.

Memory that returns

Persistent causal memory for AI agents. 295x faster than Mem0. LangChain, LlamaIndex, AutoGen, CrewAI. Rust, zero deps.